Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety bar is low. The description still adds real context beyond them: it is free to call, results are ordered best-match-first, and results are per-register with country narrowing to a single register. It does not mention what happens on zero matches or result-set size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the search keys, then sources, then result shape, then the country narrowing — a logical progression in two sentences with no filler. It is dense and packs a lot into a long first sentence, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description carries the burden of describing returns, and it does list the returned fields (id, country, number, status, city, industry, founding date) plus ordering. Missing pieces are minor but real: nothing on empty results, pagination beyond limit, or how to follow up with companies_get once an id is found.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the description meaningfully extends it: query accepts a company name, an id, or a German register number in a concrete notation ('HRB 2001 Augsburg'), which the schema never shows. Country is reinforced as ISO with example, though limit (1-25, default 10) is left entirely to the schema with no explanation of its effect.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (company search) and enumerates the exact registers/sources it covers (Companies House, France, Norway, Finland, SEC, GLEIF), which is what distinguishes it from siblings like companies_get, lookup_company, or crm_find_companies. An agent knows immediately this is the broad multi-register lookup, not a CRM or single-record lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: 'give country (ISO, e.g. FR) to ask one register' tells the agent how to narrow scope, and 'best match first' hints at ranking. But it never explicitly routes the agent away from companies_get (fetch a known company), companies_match, or companies_financials, nor states when a search would be the wrong tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.